REVIEW 3 cited by
HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The Shapley value is widely regarded as a trustworthy attribution metric. However, when people use Shapley values to explain the attribution of input variables of a deep neural network (DNN), it usually requires a very high computational cost to approximate relatively accurate Shapley values in real-world applications. Therefore, we propose a novel network architecture, the HarsanyiNet, which makes inferences on the input sample and simultaneously computes the exact Shapley values of the input variables in a single forward propagation. The HarsanyiNet is designed on the theoretical foundation that the Shapley value can be reformulated as the redistribution of Harsanyi interactions encoded by the network.
Forward citations
Cited by 3 Pith papers
-
Composing Linear Layers from Irreducibles
A rotor-based layer built from bivector exponentials approximates LLM attention projections with O(log^2 d) parameters and competitive downstream performance.
-
INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
INTER is a training-free logit-correction method that adds Harsanyi interaction scores to selected keyword tokens, lowering hallucination on six LVLM benchmarks.
-
Shapley Value-driven Data Pruning for Recommender Systems
SVV prunes recommender training interactions by their estimated Shapley value contribution to autoencoder loss reduction, reporting modest accuracy gains on four datasets but resting on a faulty value-function derivation.
Discussion (0). Sign in to comment.